Spaces:
Runtime error
Runtime error
File size: 2,125 Bytes
95395b5 3460fd7 44e69f7 95395b5 3460fd7 95395b5 3460fd7 95395b5 3460fd7 95395b5 3460fd7 95395b5 3460fd7 95395b5 3460fd7 95395b5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 |
import gradio as gr
from huggingface_hub import InferenceClient
import torch
from TTS.api import TTS
import soundfile as sf
import os
os.system("pip install fairseq==0.12.2")
# Load TTS Model (supports multiple models)
tts_model = TTS("tts_models/en/ljspeech/tacotron2-DDC").to("cuda" if torch.cuda.is_available() else "cpu")
# Hugging Face LLM client
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
messages = [{"role": "system", "content": system_message}]
for val in history:
if val[0]:
messages.append({"role": "user", "content": val[0]})
if val[1]:
messages.append({"role": "assistant", "content": val[1]})
messages.append({"role": "user", "content": message})
response = ""
for message in client.chat_completion(
messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
):
token = message.choices[0].delta.content
response += token
yield response, None # Yielding text response first
# Generate speech from text response
output_audio_path = "response.wav"
tts_model.tts_to_file(text=response, file_path=output_audio_path)
yield response, output_audio_path # Yielding audio response
# Gradio Chat Interface with Audio Output
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
gr.Slider(
minimum=0.1,
maximum=1.0,
value=0.95,
step=0.05,
label="Top-p (nucleus sampling)",
),
],
outputs=[
gr.Textbox(label="Generated Response"),
gr.Audio(type="filepath", label="TTS Output"),
],
)
if __name__ == "__main__":
demo.launch()
|